Fusing the pertinence of natural scene statistics-based methods and the ubiquity of convolutional neural network-based methods, a no-reference image quality assessment (IQA) method fusing deep learning and statistical visual features for no-reference image quality assessment (FDSVIQA) is proposed. For the statistical visual features, a local normalized luminance map and a local normalized local binary pattern (LBP) map of the image are constructed, and the local normalized luminance features and the gradient-weighted local normalized LBP features are extracted on the two maps, respectively. These two kinds of features are concatenated to build the image statistical visual features. For deep learning, the local normalized luminance block and the localized normalized LBP block are input into a double-path deep learning network, and the statistical visual features are input into the deep learning network to be integrated with the depth features. After learning and training, IQA is achieved. The performance of the proposed FDSVIQA algorithm is tested on the Laboratory for Image and Video Engineering (LIVE), LIVE Multiply Distorted Image Quality Database, and Multiply Distortion Optics Remote Sensing Image databases. Experimental results show that the FDSVIQA algorithm has excellent subjective and objective consistency and good robustness for both distorted natural images and distorted remote sensing images. In addition, the FDSVIQA has database independence.
Satellite vibrations would lead to image motion blur. Since the vibration isolators cannot fully suppress the influence of vibrations, image restoration methods are usually adopted, and the vibration characteristics of imaging system are usually required as algorithm inputs for better restoration results, making the vibration measurement error strongly connected to the final outcome. If the measurement error surpass a certain range, the restoration may not be implemented successfully. Therefore it is important to test the applicable scope of restoration algorithms and control the vibrations within the range, on the other hand, if the algorithm is robust, then the requirements for both vibration isolator and vibration detector can be lowered and thus less financial cost is needed. In this paper, vibration-induced degradation is first analyzed, based on which the effects of measurement error on image restoration are further analyzed. The vibration-induced degradation is simulated using high resolution satellite images and then the applicable working condition of typical restoration algorithms are tested with simulation experiments accordingly. The research carried out in this paper provides a valuable reference for future satellite design which plan to implement restoration algorithms.
We propose an in-orbit modulation transfer function (MTF) statistical estimation algorithm based on natural scene, called SeMTF. The algorithm can estimate the in-orbit MTF of a sensor from an image without specialized targets. First, the power spectrum of a satellite image is analyzed, then a two-dimensional (2-D) fractal Brownian motion model is adopted to represent the natural scene. The in-orbit MTF is modeled by a parametric exponential function. Subsequently, the statistical model of satellite imaging is established. Second, the model is solved by the improved profile-likelihood function method. In order to handle the nuisance parameter in the profile-likelihood function, we divided the estimation problem into two minimization problems for the parameters of the MTF model and nuisance parameters, respectively. By alternating the two iterative minimizations, the result will converge to the optimal MTF parameters. Then the SeMTF algorithm is proposed. Finally, the algorithm is tested using real satellite images. Experimental results indicate that the estimation of MTF is highly accurate.
We propose a generalized version of Akaike's information criterion (AIC) as a novel criterion for estimating a point spread function (PSF) from the degraded image only. We first show that the generalized AIC (G-AIC) is equivalent to quadratic prediction loss up to some constant, and prove that incorporating exact smoother filtering, the minimization of the prediction loss yields exact estimate of PSF. The PSF is obtained by minimizing this G-AIC over a family of approximated smoother filterings. Based on this estimated blur kernel, we then perform non-blind deconvolution using our recently proposed SURE-LET algorithm. The proposed framework is exemplified with a number of parametric PSF. The experimental results demonstrate that the minimization of this criterion yields highly accurate estimates of the PSF parameters, which also result in a negligible loss of visual quality, compared to that obtained with the exact PSF. The highly competitive results show the great potential of developing more powerful blind deconvolution algorithms based on this criterion.
A new method is proposed to solve the problem of image restoration of high resolution TDICCD camera due to satellite
vibrations, which considers image blur and irregular sampling geometric quality degradation simultaneously. Firstly, the
image quality degradation process is analyzed according to imaging characteristics of TDICCD camera, owing to image
motions during TDICCD integration time induced by satellite vibrations. In addition, the vibration simulation model is
established, and the irregular sampling degradation process of geometric quality is mathematically modeled using
bicubic Hermite interpolation. Subsequently, a full image degradation model is developed combined with blurred and
noisy degradation process. On this basis, a new method of image restoration is presented, which can implement not only
deblurring but also irregular to regular sampling. Finally, the method is verified using real remote sensing images, and
compared with the recent restoration methods. Experimental results indicate that the proposed method performs well,
and the Structural Similarity between the restored and ideal images are greater than 0.9 in the case of seriously blurred,
irregularly sampled and noisy images. The proposed method can be applied to restore high resolution on-orbit satellite